dorkos: Skill for Claude Code

.agents/skills/writing-changelogs/SKILL.md

writing-changelogs is a skill for Claude Code, Codex from dork-labs/dorkos. It costs 31 tokens per session (2,995 once invoked), scanned A, original, MIT.

A writing guide for clear changelog entries and release notes. A changelog records changes in a product, while release notes explain those changes to users.

In plain words
What is it for?
Use it to write or review changelog fragments, prepare release notes, check release quality, or rewrite commit messages for users.
Why use it?
It helps turn technical commit messages into descriptions people can understand. It also provides a consistent process for storing unreleased changes before publication.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is dork-labs/dorkos's own configuration. It tells Claude Code and Codex how to work on dorkos itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dorkos configures →

Part of the flow plugin — 32 skills, 43 commands, 5 agents, 4 hooks shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to dork-labs/dorkos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dork-labs/dorkos/main/.agents/skills/writing-changelogs/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dork-labs/dorkos

Made for: Claude Code, Codex.

Or install flow, the plugin that ships this one along with the rest of its 32 skills, 43 commands, 5 agents, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for writing-changelogs

README.md
[![agentmods](https://agentmods.dev/badge/skills/dork-labs/dorkos/writing-changelogs/github.svg)](https://agentmods.dev/skills/dork-labs/dorkos/writing-changelogs)
Your own site
<a href="https://agentmods.dev/skills/dork-labs/dorkos/writing-changelogs"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/writing-changelogs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for writing-changelogs

Your own site · 80×15
<a href="https://agentmods.dev/skills/dork-labs/dorkos/writing-changelogs"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/writing-changelogs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,995 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.02995
Opus 5 $0.00015 $0.01497
Sonnet 5 $0.00006 $0.00599
Haiku 4.5 $0.00003 $0.00299

Measured 10d ago against content hash 19ec95c74e18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

writing-changelogs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/writing-changelogs/SKILL.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Changelogs

Write changelog entries and release notes that humans actually want to read. This skill activates when writing changelog entries, preparing GitHub releases, or reviewing release notes quality.

Sources: Keep a Changelog, Common Changelog

When to Use

  • Writing a changelog fragment for a change
  • Preparing GitHub release notes via /system:release
  • Reviewing changelog entries before release
  • Transforming commit messages into user-friendly descriptions

Where entries live: fragments

Unreleased entries do not go in CHANGELOG.md. Each change adds one fragment file under changelog/unreleased/ — a coordination-free scheme that keeps parallel worktrees from colliding on a shared [Unreleased] block (ADR 260707-231641; full guide in changelog/README.md). The workflow:

  • Filename<YYMMDD-HHMMSS>-<kebab-slug>.md: a timestamp id from .claude/scripts/id.ts followed by a short slug. The post-commit hook names it from your commit subject.
  • Body — optional covers: frontmatter (which commits this fragment covers; the post-commit hook fills it in, and the PR check reads it so your prose stays free to be rewritten for a human), then one or more ### Category headings (Added, Changed, Deprecated, Removed, Fixed, Security) with bullets written per the principles below. One fragment may carry multiple categories.
  • Creation — the post-commit hook writes a fragment from each conventional commit; curate it (or hand-author one) before opening a PR. Never edit CHANGELOG.md's [Unreleased] section — it no longer holds entries.
  • Release/system:release compiles all fragments into the new ## [X.Y.Z] section and deletes them. Only the release process writes CHANGELOG.md.

The entry-quality guidance below applies identically to fragment bullets.

Core Principles

Changelog entries are user-facing prose, so the writing-for-humans skill sets the readability bar: 9th-grade level, one idea per sentence, benefit before mechanism, every acronym glossed. Read it first. The rules specific to changelogs:

Read the full file on GitHub · 266 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 266 lines · 31 tokens per session scan A 19ec95c74e18

Subscribe to this mod's changes

writing-changelogs is a skill published in the GitHub repository dork-labs/dorkos (9 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 2,995 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.